vllm-project

vllm-project/vllm

active

A high-throughput and memory-efficient inference and serving engine for LLMs

Python View on GitHub

Stars

96,412

Forks

24,461

Open issues

2,798

24h

+57

+0.1%

7d

+374

+0.4%

Refresh

30m

Star history (7 days)

Last checked

22m ago

Last pushed

40m ago

Next check

just now